Answer in brief
CVE-2026-54044 records a High severity (CVSS 7.7) vulnerability in LibreChat: Shared-Agent Editor Can Exfiltrate Owner Action API Keys via OpenAPI Spec Swap. The current sources do not mark it as known exploited. The current feed maps LibreChat-AI/LibreChat (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.7. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps LibreChat-AI/LibreChat (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| LibreChat-AI/LibreChatgeneric | <0.8.7 | 0.8.7 |
Published upstream
Nov 20, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Nov 20, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Nov 20, 2026
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. Prior to 0.8.7, POST /api/agents/actions/:agent_id in api/server/routes/agents/actions.js loads an existing action with owner credentials and merges editor-controlled metadata.domain and metadata.raw_spec while preserving metadata.api_key and related OAuth client secrets. A collaborator with EDIT permission can repoint an action to an attacker-controlled host, and a later tool invocation decrypts and sends the retained owner credential to that destination. This issue is fixed in version 0.8.7.
Quoted source text, attributed separately from HOL analysis.